© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108116
    Prev
    Next
    INDEX
    Explanations

    phrases referring to sports transfers and player movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essa
    -0.07
    owitz
    -0.07
    agara
    -0.06
     ÐĴики
    -0.06
     speech
    -0.06
    yer
    -0.06
    ëıĦë³Ħ
    -0.06
    ós
    -0.06
    ĵĺ
    -0.06
    etti
    -0.06
    POSITIVE LOGITS
    otime
    0.07
    opers
    0.07
    ITE
    0.07
    orny
    0.07
     reports
    0.06
    unya
    0.06
     Reports
    0.06
     complication
    0.06
     بع
    0.06
    ÃŃnh
    0.06
    Activations Density 0.010%

    No Known Activations